CAJ | 학술논문

提出了一种交互式分割传统CT图像肝脏肿瘤的方法。首先对CT切片进行预处理，包括肝脏薄壁组织分割及其对比增强处理，通过分水岭转换后肝脏体积被分成许多集水盆地。然后，在用户选择种子点上训练支持向量机分类来抽取肝脏肿瘤，而在分水岭转换后产生的每个小区域基础上，计算对应的用于训练和预测的特征向量。最后，在整个分割二级制体数据中执行一些形态学操作，重新定义支持向量机分类的粗糙分割结果。实验结果表明：改进方法提高了诊疗的准确性、有效性，以及在临床应用中的可行性。
제출료일충교호식분할전통CT도상간장종류적방법。수선대CT절편진행예처리，포괄간장박벽조직분할급기대비증강처리，통과분수령전환후간장체적피분성허다집수분지。연후，재용호선택충자점상훈련지지향량궤분류래추취간장종류，이재분수령전환후산생적매개소구역기출상，계산대응적용우훈련화예측적특정향량。최후，재정개분할이급제체수거중집행일사형태학조작，중신정의지지향량궤분류적조조분할결과。실험결과표명：개진방법제고료진료적준학성、유효성，이급재림상응용중적가행성。
In this paper, we present an interactive method for liver tumor segmentation from computed to-mography (CT) scans. After some pre-processing operations, including liver parenchyma segmentation and liv-er contrast enhancement, the CT volume is divided into a lot of catchment basins through watershed transform. Then a support vector machines (SVM) classifier is trained on the user-selected seed points to extract tumors from liver parenchyma, while the corresponding feature vector for training and prediction is computed based upon each small region produced by watershed transform. Finally, some morphological operations are per-formed on the whole segmented binary volume to refine the rough segmentation result of SVM classification. The experiment results show the improved method improves the diagnosis accuracy, effectiveness, and feasibil-ity in clinical application.